© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 27406
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate structure and transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.06
     Poz
    -0.06
    055
    -0.06
    Verbose
    -0.06
     brav
    -0.06
     circumstances
    -0.06
    fox
    -0.06
    entre
    -0.06
    ANGE
    -0.06
     Vict
    -0.06
    POSITIVE LOGITS
    ypad
    0.07
     migrationBuilder
    0.06
    ModelIndex
    0.06
    Automation
    0.06
    paged
    0.06
    arian
    0.06
    zin
    0.06
    ãĤº
    0.06
    CanBe
    0.06
    annes
    0.06
    Activations Density 0.000%

    No Known Activations